The proposal of Cloud/Fog Automation introduces a new architecture for industrial automation, which breaks the boundaries between information technology, operational technology, and communication technology domains, facilitating information sharing and optimizing the system as a whole. This paper extends the vision of Cloud/Fog Automation to scalable robotics, which is deployed across the device-edge-cloud continuum using cloud-native technologies and calls for a co-design methodology that jointly considers communication, compute, and application characteristics. From an industrial practitioner’s viewpoint, we demonstrate its feasibility with a comprehensive approach to optimizing a mobile robot application. We leverage a dual-phase optimization strategy: static optimization pre-deployment and dynamic optimization post-deployment. In the static optimization phase, we employ a profiling-based method to minimize communication overhead while balancing computational load. The dynamic optimization phase utilizes a reinforcement learning-based approach to explore an optimal policy for computation offloading and network quality of service configuration to maximize edge server utilization and lower network usage costs while guaranteeing application performance. Experimental results, validated through a Simulation-to-Reality (Sim-to-Real) approach, demonstrate that our co-design method significantly enhances operational efficiency, reduces network costs, and improves overall system responsiveness.

With the emergence of edge computing, the problem of offloading jobs between an Edge Device (ED) and an Edge Server (ES) received significant attention in the past. Motivated by the fact that an increasing number of applications are using Machine Learning (ML) inference from the data samples collected at the EDs, we study the problem of offloadinginference jobsby considering the following novel aspects: 1) in contrast to a typical computational job, the processing time of an inference job depends on the size of the ML model, and 2) recently proposed Deep Neural Networks (DNNs) for resource-constrained devices provide the choice of scaling down the model size by trading off the inference accuracy. Considering that multiple ML models are available at the ED, and a powerful ML model is available at the ES, we formulate an Integer Linear Programming (ILP) problem with the objective of maximizing the total inference accuracy of$n$data samples at the ED subject to a time constraint$T$on the makespan. Noting that the problem is NP-hard, we propose an approximation algorithm Accuracy Maximization using LP-Relaxation and Rounding (AMR$^{2}$) and prove that it results in a makespan at most$\text{2}T$and achieves a total accuracy that is lower by a small constant from the optimal total accuracy implying that AMR$^{2}$is asymptotically optimal. Further, if the data samples are identical we propose Accuracy Maximization using Dynamic Programming (AMDP), an optimal pseudo-polynomial time algorithm. Furthermore, we extend AMR$^{2}$for the case of multiple ESs, where each ES is equipped with a powerful ML model. As proof of concept, we implemented AMR$^{2}$on a Raspberry Pi, equipped with MobileNets, that is connected to a server equipped with ResNet, and studied the total accuracy and makespan performance of AMR$^{2}$for image classification.

With the emergence of edge computing, the problem of offloading jobs between an Edge Device (ED) and an Edge Server (ES) received significant attention in the past. Motivated by the fact that an increasing number of applications are using Machine Learning (ML) inference from the data samples collected at the EDs, we study the problem of offloading inference jobs by considering the following novel aspects: in contrast to a typical computational job 1) both inference accuracy and processing time of an inference job increase with the size of the ML model and 2)recently proposed Deep Neural Networks (DNNs) for resource-constrained EDs provide the choice of scaling down the model size by trading off the inference accuracy. Therefore, we consider that multiple small-size ML models are available at the ED and a powerful large-size ML model is available at the ES, and study a general assignment problem with the objective of maximizing the total inference accuracy for the data samples at the ED subject to a time constraint T on the makespan. Noting that the problem is NP-hard, we propose an approximation algorithm: Accuracy Maximization using LP-Relaxation and Rounding (AMR2), and prove that it results in a makespan at most 2T, and achieves a total accuracy that is lower by a small constant from the optimal total accuracy. As proof of concept, we implemented AMR2 on a Raspberry Pi, equipped with MobileNets, that is connected via LAN to a server equipped with ResNet, and studied the total accuracy and makespan performance of AMR2 for image classification.